University of Sussex
Browse

Optimising agile social media analysis

Download (0.48 kB)
presentation
posted on 2023-06-09, 01:30 authored by Thomas Kober, David WeirDavid Weir
Agile social media analysis involves building bespoke, one-off classification pipelines tailored to the analysis of specific datasets. In this study we investigate how the DUALIST architecture can be optimised for agile social media analysis. We evaluate several semi-supervised learning algorithms in conjunction with a Na ¨ive Bayes model, and show how these modifications can improve the performance of bespoke classifiers for a variety of tasks on a large range of datasets.

History

Publication status

  • Published

File Version

  • Published version

Page range

31-40

Presentation Type

  • paper

Event name

6th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis (WASSA 2015)

Event location

Lisbon

Event type

workshop

Event date

17th September 2015

Department affiliated with

  • Informatics Publications

Full text available

  • Yes

Peer reviewed?

  • Yes

Legacy Posted Date

2016-06-06

First Open Access (FOA) Date

2016-06-06

First Compliant Deposit (FCD) Date

2016-06-06

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC